© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 70438
    Prev
    Next
    INDEX
    Explanations

    Hunter unexpectedly

    np_acts-logits-general · gemini-2.5-flash-lite

    family values and ties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    STUD
    0.47
    食堂
    0.47
    Consider
    0.45
    Jeśli
    0.45
    [
    0.43
    urno
    0.42
    মুখ
    0.42
    Dopo
    0.41
    Hor
    0.41
    Scient
    0.41
    POSITIVE LOGITS
     संस्कारों
    0.48
     பேச்சு
    0.47
     Designs
    0.46
    kaŭ
    0.46
     ମ
    0.46
     ピン
    0.46
     राइड
    0.45
     デザイン
    0.44
     Davis
    0.44
    uminação
    0.44
    Activations Density 0.000%

    No Known Activations